earticle

영어

Formative modeling has been widely used as an alternative to reflective modeling in IS and behavioral research. However, several recent studies have raised questions about its reliability and the research community is divided into its proponents and opponents. Existing studies that attempted the validity testing of a formative model have primarily focused on its estimation stability in the context of varying relationships between a formative construct and the choice of dependent constructs (consequences). In this research, we examine the reliability issue through the lens of a formative construct’s indicators. More specifically, the focus is to study implications of collinearity among formative measures on indicator weight, construct error variance, and structural path coefficient of a formative model. For this, we first frame theoretical expectations that associate the properties of collinearity with the three validity dimensions. Then empirical tests are conducted based on a real survey-based covariance matrix provided by Diamantopoulus (2011) and the results are matched against theoretical expectations to judge the stability of formative modeling.